Fast calculations of total unduplicated reach and frequency statistics

A computer implemented method for performing a total unduplicated reach and frequency analysis performed via a turf analysis application executing in a distributed data processing environment, the method comprising:

• receiving a plurality of variables containing numerical or textual values from a data store;
• in response applying a weight to the plurality of variables based on a first user selection input, via a user device, identifying a subset of variables of the plurality of variables, wherein the subset of variables is identified based on the associated weight meeting a product reach criteria value;
• partitioning the subset of variables into a plurality of groups of variables, wherein the groups of variables are partitioned based on an associated weight rank value, wherein each of the plurality of groups of variables contains less than a predetermined maximum number of variables;
• calculating a reach score for each group of variables of the plurality of groups of variables;
• wherein the reach score is based on a first total unduplicated reach and frequency analysis;
• identifying at least one group of variables, of the plurality of groups of variables that has a reach score above a first threshold value;
• communicating, for display via the user device, the identified at least one group of variables and associated reach score and a set of first total unduplicated reach and frequency analysis results to the user;
• receiving a second user selection input from the user, wherein the second user selection input modifies one or more variables of the at least one group of variables;
• determining, using a processor that periodically determines at least one available resource of the computer for performing the total unduplicated reach and frequency analysis, an available computational resource value;
• and
• in response to a determination that a count of identified variables of the modified at least one group of variables is below a second threshold value, wherein the second threshold value is based on the determined available computational resource value, performing a second total unduplicated reach and frequency analysis, of the identified at least one group of variables.